© 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. 47336
    Prev
    Next
    INDEX
    Explanations

    angiotensin

    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
    Slope
    -0.08
     hover
    -0.08
     adjud
    -0.08
    .sw
    -0.08
    -hover
    -0.08
    ిష
    -0.07
    Hover
    -0.07
    Sw
    -0.07
    (ne
    -0.07
    Inclus
    -0.07
    POSITIVE LOGITS
    zu
    0.09
    狂
    0.08
     Generated
    0.08
     III
    0.08
     VI
    0.08
     Occidental
    0.08
     VIII
    0.08
    VI
    0.08
     VII
    0.07
     backstage
    0.07
    Activations Density 0.000%

    No Known Activations