© 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. 48007
    Prev
    Next
    INDEX
    Explanations

    horses

    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
     Masse
    -0.08
     cov
    -0.07
    �
    -0.07
     covariance
    -0.07
     standalone
    -0.07
    <'
    -0.07
    (that
    -0.07
     CF
    -0.06
    (using
    -0.06
     coul
    -0.06
    POSITIVE LOGITS
     waarop
    0.08
    קום
    0.08
    екта
    0.08
     vaiht
    0.08
     Estimates
    0.08
     geeign
    0.08
     enemy
    0.08
     condam
    0.08
     troops
    0.08
    患
    0.07
    Activations Density 0.004%

    No Known Activations