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. 43662
    Prev
    Next
    INDEX
    Explanations

    between

    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
    Sto
    -0.08
     Bolivia
    -0.07
     Coupe
    -0.07
    -Compatible
    -0.07
     Cyber
    -0.07
     Oy
    -0.07
     इसके
    -0.07
    _GAIN
    -0.07
     arac
    -0.07
     graduated
    -0.07
    POSITIVE LOGITS
    ner
    0.08
    034
    0.08
    罪
    0.08
    男子
    0.08
     casually
    0.07
    男人
    0.07
    探
    0.07
     distancia
    0.07
     (**
    0.07
     ur
    0.07
    Activations Density 0.016%

    No Known Activations