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. 43092
    Prev
    Next
    INDEX
    Explanations

    reflecting

    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
     nadr
    -0.08
    <Row
    -0.07
     réelle
    -0.07
    antiation
    -0.07
    witz
    -0.07
     Wy
    -0.07
     Leit
    -0.07
     региона
    -0.07
     Clever
    -0.07
     assol
    -0.07
    POSITIVE LOGITS
     sø
    0.08
     kett
    0.08
     sunscreen
    0.08
     noc
    0.07
     पस
    0.07
     nws
    0.07
     Studien
    0.07
     dmg
    0.07
     calming
    0.07
    Dav
    0.07
    Activations Density 0.004%

    No Known Activations