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. 12441
    Prev
    Next
    INDEX
    Explanations

    A

    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
    _base
    -0.08
     multiples
    -0.08
    gea
    -0.07
     proportional
    -0.07
    (auto
    -0.07
    (float
    -0.07
    azana
    -0.07
     MHz
    -0.07
    -0.07
     multiplying
    -0.06
    POSITIVE LOGITS
    enticator
    0.08
    -vis
    0.08
     ontmo
    0.08
    ключ
    0.07
     vervolg
    0.07
     verble
    0.07
    $post
    0.07
    redentials
    0.07
     inquiet
    0.07
    /photo
    0.07
    Activations Density 0.013%

    No Known Activations