© 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. 105
    Prev
    Next
    INDEX
    Explanations

    rog/ог

    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
     fingerprint
    -0.09
     סימ
    -0.08
    ord
    -0.08
    Fingerprint
    -0.08
    اته
    -0.08
    ayo
    -0.07
    قبال
    -0.07
     biom
    -0.07
    dice
    -0.07
    Mom
    -0.07
    POSITIVE LOGITS
     Ate
    0.08
    ଧ
    0.08
     nous
    0.08
     ate
    0.08
     Odisha
    0.07
     Nous
    0.07
    ူ
    0.07
     Body
    0.07
    Talent
    0.07
    (Cs
    0.07
    Activations Density 0.001%

    No Known Activations