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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1258
    Prev
    Next
    INDEX
    Explanations

    requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    digest
    -0.08
     dyn
    -0.07
     ක
    -0.07
    datas
    -0.07
    esses
    -0.07
    _FALSE
    -0.07
     Zusamm
    -0.07
    _testing
    -0.07
     سالن
    -0.07
    rin
    -0.07
    POSITIVE LOGITS
    \Json
    0.08
    aksi
    0.08
    \Product
    0.08
    �
    0.07
    ;t
    0.07
     Skrill
    0.07
    াত্র
    0.07
    .unit
    0.07
    lela
    0.07
    \Http
    0.07
    Activations Density 0.000%

    No Known Activations