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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1584
    Prev
    Next
    INDEX
    Explanations

    freed

    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
     поддержку
    -0.08
     좋
    -0.08
    도를
    -0.08
     ended
    -0.08
    _trait
    -0.07
     рада
    -0.07
    %%%
    -0.07
     allele
    -0.07
     görüş
    -0.07
    esu
    -0.07
    POSITIVE LOGITS
    over
    0.08
    über
    0.08
    yle
    0.08
    kal
    0.08
    ysin
    0.08
     FL
    0.07
     explos
    0.07
    azine
    0.07
     crust
    0.07
     flashes
    0.07
    Activations Density 0.001%

    No Known Activations