Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43273
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
     monitoring
    -0.09
     personalidade
    -0.08
    Persona
    -0.08
     vivid
    -0.08
    Pessoa
    -0.08
    兑换
    -0.08
     خرید
    -0.07
     conversa
    -0.07
    Monitoring
    -0.07
     reliably
    -0.07
    POSITIVE LOGITS
     kokku
    0.09
    bine
    0.09
     יחד
    0.08
     bod
    0.08
    াংশ
    0.08
    abadde
    0.08
    buquerque
    0.08
    剩
    0.08
    ವಸ್ಥ
    0.08
    bined
    0.08
    Activations Density 0.051%

    No Known Activations