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. 8447
    Prev
    Next
    INDEX
    Explanations

    command

    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
     inatt
    -0.08
     quantit
    -0.08
     unused
    -0.08
     και
    -0.07
     phenomena
    -0.07
     memberships
    -0.07
    agra
    -0.07
     avail
    -0.07
     biod
    -0.07
    кість
    -0.07
    POSITIVE LOGITS
     Leute
    0.07
    代理
    0.07
     Goed
    0.07
    582
    0.07
    .Rotate
    0.07
     Wehr
    0.07
     bein
    0.07
     Armada
    0.07
    물을
    0.07
     drugih
    0.07
    Activations Density 0.000%

    No Known Activations