© 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. 19-RESID-POST-AA
    11. 103075
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.08
     YOU
    -0.08
     java
    -0.08
     DERECHO
    -0.08
     FIVE
    -0.08
     HOLD
    -0.08
     DAILY
    -0.08
    Mixin
    -0.08
     FOR
    -0.08
     malunga
    -0.08
    POSITIVE LOGITS
    (help
    0.10
    =h
    0.09
    )=
    0.09
    .Help
    0.09
    ')->
    0.09
    help
    0.09
     সাহায
    0.09
    ?)
    0.09
    (dest
    0.09
    =s
    0.08
    Activations Density 0.001%

    No Known Activations