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. 3-RESID-POST-AA
    6. 1975
    Prev
    Next
    INDEX
    Explanations

    expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     жыл
    -0.08
     amist
    -0.08
     Flu
    -0.08
    acal
    -0.08
     FRIEND
    -0.08
     rats
    -0.08
     chemotherapy
    -0.08
     দুর
    -0.08
    .Proxy
    -0.08
     الحساب
    -0.08
    POSITIVE LOGITS
     mosaic
    0.08
     projects
    0.08
     vandal
    0.07
     chans
    0.07
     inclination
    0.07
    inian
    0.07
     avenues
    0.07
     incl
    0.07
     indie
    0.07
     contest
    0.07
    Activations Density 0.016%

    No Known Activations