© 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. 1340
    Prev
    Next
    INDEX
    Explanations

    code, compilation, configuration

    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
    istre
    -0.08
    स्था
    -0.08
    wah
    -0.07
    	Local
    -0.07
    licing
    -0.07
     Fr
    -0.07
     иг
    -0.07
    stract
    -0.07
    mvc
    -0.07
     abusive
    -0.07
    POSITIVE LOGITS
     chan
    0.08
     erstellen
    0.08
     dib
    0.08
     modd
    0.07
    �
    0.07
     exported
    0.07
     disen
    0.07
    _export
    0.07
     agb
    0.07
    ťa
    0.07
    Activations Density 0.000%

    No Known Activations