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

    Neuronpedia

    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. 78046
    Prev
    Next
    INDEX
    Explanations

    positive, negative, inequalities

    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
    raid
    -0.08
     vien
    -0.08
    ra
    -0.08
     reducir
    -0.08
     mà
    -0.08
     raid
    -0.07
    Implemented
    -0.07
     realidad
    -0.07
     neer
    -0.07
     Upon
    -0.07
    POSITIVE LOGITS
     until
    0.14
     solange
    0.14
    until
    0.13
    Until
    0.13
     Until
    0.12
    続
    0.12
    まだ
    0.12
    _until
    0.12
    直到
    0.12
    Continue
    0.11
    Activations Density 0.031%

    No Known Activations