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. 78075
    Prev
    Next
    INDEX
    Explanations

    istel

    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
     internationaux
    -0.09
    Included
    -0.08
     uncl
    -0.08
     ancora
    -0.08
     sakit
    -0.08
    ト
    -0.08
     ridiculously
    -0.07
     trx
    -0.07
     incluidos
    -0.07
    Intermediate
    -0.07
    POSITIVE LOGITS
     Quest
    0.08
    qan
    0.08
     XOR
    0.08
    xor
    0.08
    Quest
    0.07
    ngwe
    0.07
    ńc
    0.07
    дання
    0.07
    114
    0.07
    tsi
    0.07
    Activations Density 0.000%

    No Known Activations