© 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. 3-RESID-POST-AA
    11. 1310
    Prev
    Next
    INDEX
    Explanations

    use

    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
    Nancy
    -0.09
    Bj
    -0.08
    and
    -0.07
    Lift
    -0.07
    nant
    -0.07
     जानते
    -0.07
    Cara
    -0.07
     GK
    -0.07
    lat
    -0.07
    ologies
    -0.07
    POSITIVE LOGITS
     insulated
    0.09
     Henri
    0.08
    筋
    0.07
     benef
    0.07
     crush
    0.07
     scented
    0.07
     Mop
    0.07
     Crush
    0.07
     PATCH
    0.07
     Campo
    0.07
    Activations Density 0.000%

    No Known Activations