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. 53978
    Prev
    Next
    INDEX
    Explanations

    now

    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
     opposed
    -0.08
    chief
    -0.08
    ogue
    -0.08
    قاذ
    -0.07
    ,in
    -0.07
    ,get
    -0.07
     strained
    -0.07
    ottest
    -0.07
    he
    -0.07
    ce
    -0.07
    POSITIVE LOGITS
     Universidade
    0.08
     mulher
    0.07
     pou
    0.07
    UDENT
    0.07
    mall
    0.07
    0.07
    _POP
    0.07
    �
    0.07
    _SEPARATOR
    0.07
    उ
    0.07
    Activations Density 0.001%

    No Known Activations