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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70090
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     ecstatic
    -0.08
     Edith
    -0.08
     جيئن
    -0.08
     �
    -0.08
     πή
    -0.08
     פס
    -0.08
    Emotion
    -0.08
    etros
    -0.08
     حسين
    -0.08
     adrenal
    -0.07
    POSITIVE LOGITS
     CNC
    0.09
    _FR
    0.08
    _C
    0.08
     outer
    0.07
     highly
    0.07
    ambi
    0.07
     যোগাযোগ
    0.07
    neq
    0.07
    792
    0.07
     Fees
    0.07
    Activations Density 0.022%

    No Known Activations