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. 88055
    Prev
    Next
    INDEX
    Explanations

    mass units and numbers

    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
     വിവരം
    -0.07
    总部
    -0.07
     Bast
    -0.07
     Tarr
    -0.07
    미
    -0.07
     적극
    -0.07
    积极
    -0.07
     Möglich
    -0.07
     إل
    -0.07
    ']);
    -0.07
    POSITIVE LOGITS
    .pg
    0.11
    の場合
    0.10
     শিশ
    0.09
    (pg
    0.09
     pg
    0.09
    (helper
    0.09
    _pg
    0.09
     thì
    0.09
     બાળક
    0.09
     দিনে
    0.08
    Activations Density 0.046%

    No Known Activations