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

    Neuronpedia

    APICircuit 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. 106250
    Prev
    Next
    INDEX
    Explanations

    Configurations, instructions

    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
     grill
    -0.09
     makeup
    -0.09
     initials
    -0.08
     পো
    -0.08
     dwelling
    -0.08
    邀请
    -0.08
     dwell
    -0.08
     grills
    -0.08
     punctuation
    -0.07
    .credit
    -0.07
    POSITIVE LOGITS
    _BOOLEAN
    0.09
    _boolean
    0.08
     सुझ
    0.08
     vscode
    0.08
     Hacks
    0.08
    _ENABLE
    0.08
     sortable
    0.08
    itha
    0.08
    _OVERRIDE
    0.08
    _EXIST
    0.08
    Activations Density 0.002%

    No Known Activations