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. 58951
    Prev
    Next
    INDEX
    Explanations

    energy storage

    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
     dispoz
    -0.08
    hat
    -0.08
    @[
    -0.08
     etiquette
    -0.08
    '}
    -0.08
    @\
    -0.08
    (style
    -0.07
     uncont
    -0.07
     hat
    -0.07
    (tx
    -0.07
    POSITIVE LOGITS
     Speicherung
    0.12
     speichern
    0.10
     pérdidas
    0.10
    Paused
    0.09
     गं
    0.09
     خس
    0.09
    پار
    0.09
     almacenar
    0.09
     盐
    0.09
     ذخ
    0.09
    Activations Density 0.003%

    No Known Activations