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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 102737
    Prev
    Next
    INDEX
    Explanations

    Port numbers

    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
     engen
    -0.08
    zet
    -0.08
     gâ
    -0.08
    �
    -0.07
     valued
    -0.07
    _integr
    -0.07
    �
    -0.07
    verb
    -0.07
    ruption
    -0.07
     yer
    -0.07
    POSITIVE LOGITS
    ০
    0.08
     прым
    0.08
     otrok
    0.08
     ethics
    0.08
    ०
    0.08
    ৮
    0.08
     बजे
    0.08
    ८
    0.08
    Pid
    0.08
     pager
    0.08
    Activations Density 0.003%

    No Known Activations