Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 301
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     �
    -0.09
     Srin
    -0.08
     pertains
    -0.08
     pos
    -0.07
    	pos
    -0.07
    這
    -0.07
     positif
    -0.07
    _pos
    -0.07
     posit
    -0.07
    ,pos
    -0.07
    POSITIVE LOGITS
     duly
    0.08
    LP
    0.08
    Flush
    0.08
     dtí
    0.08
    Aggreg
    0.08
    hose
    0.08
    alom
    0.08
    (Line
    0.08
     raro
    0.07
     linewidth
    0.07
    Activations Density 0.002%

    No Known Activations