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. 42134
    Prev
    Next
    INDEX
    Explanations

    cluster computing

    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
     गृह
    -0.08
    argin
    -0.08
    mæ
    -0.08
    adena
    -0.08
     corpore
    -0.08
    ėt
    -0.08
    本人
    -0.08
     hitch
    -0.08
     Dul
    -0.08
    iane
    -0.07
    POSITIVE LOGITS
    -wide
    0.11
     members
    0.10
     Members
    0.09
     OK
    0.08
    成员
    0.08
     applications
    0.08
    members
    0.08
    wide
    0.08
     multip
    0.08
     Rwanda
    0.08
    Activations Density 0.002%

    No Known Activations