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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1061
    Prev
    Next
    INDEX
    Explanations

    identifiers and IDs

    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
     Saudi
    -0.08
     bø
    -0.08
     Masks
    -0.08
     fon
    -0.08
    .Double
    -0.08
     Liter
    -0.08
     doctorate
    -0.07
     мала
    -0.07
     την
    -0.07
    enden
    -0.07
    POSITIVE LOGITS
    કી
    0.08
    找
    0.08
    finger
    0.08
     Ferry
    0.08
    Topo
    0.07
    	c
    0.07
     prens
    0.07
     ferry
    0.07
     famoso
    0.07
    仓
    0.07
    Activations Density 0.002%

    No Known Activations