© 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. 78873
    Prev
    Next
    INDEX
    Explanations

    science and data

    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
     apost
    -0.08
     sten
    -0.08
    ស
    -0.08
    -0.07
    =create
    -0.07
     Morph
    -0.07
     punching
    -0.07
     freestyle
    -0.07
    -н
    -0.07
    decision
    -0.07
    POSITIVE LOGITS
    ::-
    0.09
    Prevent
    0.09
     Beethoven
    0.09
     Bose
    0.08
     الرو
    0.08
     decreases
    0.08
     બાળ
    0.08
    avanje
    0.08
     unavoidable
    0.08
    <java
    0.08
    Activations Density 0.001%
    No Known Activations