© 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. 11-RESID-POST-AA
    11. 95033
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NSIndex
    -0.09
    XM
    -0.09
    @Xml
    -0.08
    ক্ষ
    -0.08
    .dem
    -0.08
    ક્સ
    -0.08
    ools
    -0.08
     "::
    -0.07
    NSNotification
    -0.07
    üs
    -0.07
    POSITIVE LOGITS
     complexity
    0.08
     tag
    0.08
     Complexity
    0.08
     palab
    0.07
     espesyal
    0.07
     Tre
    0.07
     SPECIAL
    0.07
     munch
    0.07
    	tag
    0.07
     spot
    0.07
    Activations Density 0.040%

    No Known Activations