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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95572
    Prev
    Next
    INDEX
    Explanations

    =

    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
     exploitation
    -0.09
     rad
    -0.08
     thanks
    -0.07
    Equation
    -0.07
     reeks
    -0.07
    Thank
    -0.07
     ben
    -0.07
    每
    -0.07
     benen
    -0.07
    偶
    -0.07
    POSITIVE LOGITS
    _=
    0.09
     Cand
    0.09
     хэд
    0.08
    ũ
    0.08
     minas
    0.08
    _;
    ↵
    0.08
    =
    0.08
     (_,
    0.08
    				
    ↵
    0.08
     გამო�
    0.08
    Activations Density 0.016%

    No Known Activations