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. 9139
    Prev
    Next
    INDEX
    Explanations

    other

    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
    Router
    -0.08
    fee
    -0.08
     konkrete
    -0.07
     vea
    -0.07
     आपका
    -0.07
    _router
    -0.07
     kuna
    -0.07
    mynd
    -0.07
     जाए
    -0.07
     rectangles
    -0.07
    POSITIVE LOGITS
     LSU
    0.09
     quarto
    0.08
    bull
    0.08
     Pau
    0.08
     surviving
    0.07
    是在
    0.07
     TARGET
    0.07
     estágio
    0.07
     hō
    0.07
    少妇
    0.07
    Activations Density 0.176%

    No Known Activations