© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    Addresses

    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
     heredit
    -0.08
    ullie
    -0.08
    gestellt
    -0.07
     Fib
    -0.07
     représente
    -0.07
    fil
    -0.07
     برو
    -0.07
     parti
    -0.07
    Fib
    -0.07
     סוף
    -0.07
    POSITIVE LOGITS
     acct
    0.08
     gigantic
    0.08
     accommodatie
    0.07
     común
    0.07
    _CHANGED
    0.07
     boul
    0.07
    IFORM
    0.07
     pkg
    0.07
     Maße
    0.07
     confirming
    0.07
    Activations Density 0.001%

    No Known Activations