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. 88069
    Prev
    Next
    INDEX
    Explanations

    zero

    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
     refl
    -0.08
     reflective
    -0.08
    (mid
    -0.08
     Ks
    -0.08
     refleja
    -0.08
    _SEQUENCE
    -0.08
    _Do
    -0.08
    _NR
    -0.08
    (beta
    -0.07
    MAD
    -0.07
    POSITIVE LOGITS
    gro
    0.08
     মোট
    0.08
     czł
    0.08
     parking
    0.08
    gettext
    0.08
     inteiro
    0.07
    茶
    0.07
     zvinhu
    0.07
     оснащ
    0.07
    аж
    0.07
    Activations Density 0.002%

    No Known Activations