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. 102879
    Prev
    Next
    INDEX
    Explanations

    迅

    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
    निर्�
    -0.08
     electrom
    -0.07
    ssk
    -0.07
     terb
    -0.07
     निर्म
    -0.07
     vyb
    -0.07
     الوس
    -0.07
    Xt
    -0.07
     thym
    -0.07
     photon
    -0.07
    POSITIVE LOGITS
    透
    0.08
     ethn
    0.08
     phosph
    0.08
    ific
    0.07
     ethnic
    0.07
    izare
    0.07
     Bruce
    0.07
     serio
    0.07
    ucci
    0.07
    ENCE
    0.07
    Activations Density 0.001%

    No Known Activations