© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24817
    Prev
    Next
    INDEX
    Explanations

    product listings/reviews

    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
     springfox
    -0.09
     oka
    -0.08
     udara
    -0.08
     abrir
    -0.08
     संकेत
    -0.08
     Buffered
    -0.07
    'organisation
    -0.07
    iscipline
    -0.07
    .urlopen
    -0.07
     indifer
    -0.07
    POSITIVE LOGITS
     convers
    0.08
    Elevation
    0.08
     elevations
    0.08
     Elev
    0.08
    -height
    0.08
    -b
    0.07
     elevated
    0.07
     Eb
    0.07
    -left
    0.07
     elevate
    0.07
    Activations Density 0.004%

    No Known Activations