© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2792
    Prev
    Next
    INDEX
    Explanations

    base

    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
     docks
    -0.08
     yem
    -0.08
     polyester
    -0.08
    Mario
    -0.08
     Lettre
    -0.08
     lettres
    -0.08
    LK
    -0.07
     sesame
    -0.07
     semen
    -0.07
     colle
    -0.07
    POSITIVE LOGITS
    mega
    0.08
     ulo
    0.08
     skyline
    0.07
     Resist
    0.07
    əb
    0.07
     нал
    0.07
    0.07
     atmosphere
    0.07
    oplasm
    0.07
     hậu
    0.07
    Activations Density 0.001%

    No Known Activations