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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54691
    Prev
    Next
    INDEX
    Explanations

    AMP

    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
    contain
    -0.08
    contains
    -0.07
    icarbon
    -0.07
     hine
    -0.07
     Hun
    -0.07
     frontal
    -0.07
    yard
    -0.07
    -0.07
    ilon
    -0.07
     SSP
    -0.07
    POSITIVE LOGITS
    -mediated
    0.11
     influences
    0.09
     produced
    0.09
     mediated
    0.09
    ύ
    0.08
     produzido
    0.08
     steadily
    0.08
     φυσ
    0.08
     influencia
    0.08
     generated
    0.08
    Activations Density 0.007%
    No Known Activations