Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55907
    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
    Fiscal
    -0.09
     Fiscal
    -0.08
     Femme
    -0.08
    Firefox
    -0.08
     Mujeres
    -0.08
     Gon
    -0.08
     Heater
    -0.08
    Itens
    -0.08
    Agents
    -0.08
    Battery
    -0.07
    POSITIVE LOGITS
     jsonify
    0.07
     $,
    0.07
    (crate
    0.07
     ?>"
    0.07
     snd
    0.07
    rekt
    0.07
     invisible
    0.07
     corn
    0.07
     bil
    0.07
    lyt
    0.07
    Activations Density 0.001%

    No Known Activations