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. 109698
    Prev
    Next
    INDEX
    Explanations

    and

    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
     grain
    -0.08
     Atkins
    -0.08
     audiovisual
    -0.08
     taf
    -0.07
    anggung
    -0.07
     Grain
    -0.07
     grap
    -0.07
    grain
    -0.07
     Gl
    -0.07
    e
    -0.07
    POSITIVE LOGITS
     planar
    0.10
     diagon
    0.09
     geometry
    0.09
    rounded
    0.09
    near
    0.09
    Near
    0.08
    .geometry
    0.08
     nazi
    0.08
     symmetric
    0.08
     symmetrical
    0.08
    Activations Density 0.028%

    No Known Activations