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. 30214
    Prev
    Next
    INDEX
    Explanations

    trunk

    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
    Lov
    -0.08
    'amour
    -0.07
     Lov
    -0.07
     woes
    -0.07
     reluctant
    -0.07
    وہ
    -0.07
     zacz
    -0.07
    Bew
    -0.07
    держ
    -0.07
     Ville
    -0.07
    POSITIVE LOGITS
    prove
    0.09
    arly
    0.08
     Blum
    0.07
    用途
    0.07
     recomm
    0.07
     pul
    0.07
     scope
    0.07
     prip
    0.07
    orgh
    0.07
     Emmy
    0.07
    Activations Density 0.002%

    No Known Activations