© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68978
    Prev
    Next
    INDEX
    Explanations

    explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microwave
    -0.09
    Checkpoint
    -0.09
    _checkpoint
    -0.09
    _scheduler
    -0.08
     angi
    -0.08
     NVIDIA
    -0.08
     onboard
    -0.08
     horizontal
    -0.08
    _horizontal
    -0.08
     horizont
    -0.08
    POSITIVE LOGITS
     pronunciation
    0.14
     pronunci
    0.12
     vowel
    0.12
     lexical
    0.12
     spelling
    0.12
     lingü
    0.11
     linguistic
    0.11
     Bedeut
    0.11
     grammatical
    0.11
     употреб
    0.11
    Activations Density 0.079%

    No Known Activations