© 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. 7-RESID-POST-AA
    11. 1376
    Prev
    Next
    INDEX
    Explanations

    перел

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     validation
    -0.08
     R
    -0.07
    EB
    -0.07
    }@
    -0.07
     atin
    -0.07
     meas
    -0.07
    ગર
    -0.07
     મોટી
    -0.07
     luc
    -0.07
    know
    -0.06
    POSITIVE LOGITS
    bend
    0.09
    yɛ
    0.08
    .rich
    0.08
    encia
    0.08
    Signing
    0.08
    łość
    0.08
     투
    0.08
     Bryce
    0.08
    hemat
    0.08
     abge
    0.08
    Activations Density 0.001%

    No Known Activations