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. 44048
    Prev
    Next
    INDEX
    Explanations

    both

    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
    _checkpoint
    -0.09
    checkpoint
    -0.08
     leggings
    -0.08
     GK
    -0.08
     testimon
    -0.08
     checkpoint
    -0.08
    Checkpoint
    -0.08
    Clamp
    -0.07
    ISK
    -0.07
    backup
    -0.07
    POSITIVE LOGITS
    -controls
    0.08
    б
    0.08
     NOT
    0.08
    538
    0.08
    های
    0.07
    -more
    0.07
    -floating
    0.07
    هایی
    0.07
     nitrogen
    0.07
     Aside
    0.07
    Activations Density 0.014%

    No Known Activations