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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60931
    Prev
    Next
    INDEX
    Explanations

    of

    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
    acceler
    -0.09
     gala
    -0.08
    Acceler
    -0.08
     বেশি
    -0.08
    FUN
    -0.08
    altungs
    -0.08
    cantidad
    -0.08
    拳
    -0.08
    _ACCEL
    -0.08
    Cantidad
    -0.08
    POSITIVE LOGITS
     duct
    0.07
     onto
    0.07
     boundaries
    0.07
     trag
    0.07
    /bar
    0.07
     cuch
    0.07
    �
    0.07
     Bradford
    0.07
     shaft
    0.07
    ास
    0.07
    Activations Density 0.007%

    No Known Activations