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. 7-RESID-POST-AA
    6. 131064
    Prev
    Next
    INDEX
    Explanations

    Smart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prospect
    -0.07
    Str
    -0.07
    oba
    -0.07
     Öğ
    -0.07
     communic
    -0.07
    —a
    -0.07
    —with
    -0.07
     justice
    -0.06
    Hou
    -0.06
    Vict
    -0.06
    POSITIVE LOGITS
     SNAP
    0.09
    ళ
    0.09
     leash
    0.08
     narciss
    0.08
     контракт
    0.08
     kurzem
    0.08
    zn
    0.08
    NFL
    0.08
     contracts
    0.08
     вра
    0.08
    Activations Density 0.001%

    No Known Activations