© 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. 11-RESID-POST-AA
    11. 24815
    Prev
    Next
    INDEX
    Explanations

    dialogue

    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
     sagitt
    -0.09
     lar
    -0.09
     comprom
    -0.08
    asang
    -0.08
     usuários
    -0.08
    rosc
    -0.08
     fanatic
    -0.08
    硬
    -0.08
     سخت
    -0.08
     bothers
    -0.08
    POSITIVE LOGITS
     tekst
    0.08
    _text
    0.08
    양
    0.07
     ബ
    0.07
    18
    0.07
    ണം
    0.07
    am
    0.07
    ىنى
    0.07
    Kas
    0.07
     Nachrichten
    0.07
    Activations Density 0.001%

    No Known Activations