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. 90039
    Prev
    Next
    INDEX
    Explanations

    BSD

    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
     rehears
    -0.09
     misleading
    -0.08
     metaphor
    -0.08
     crore
    -0.08
     المسر
    -0.08
    매
    -0.08
    ੋਂ
    -0.08
     dysfunctional
    -0.07
    াৎ
    -0.07
    (matches
    -0.07
    POSITIVE LOGITS
     GNU
    0.08
     geç
    0.07
    -derived
    0.07
    �
    0.07
     cercano
    0.07
     '\\
    0.07
    Reached
    0.07
     Hitch
    0.07
     Moj
    0.07
     Foundation
    0.07
    Activations Density 0.003%

    No Known Activations