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. 24007
    Prev
    Next
    INDEX
    Explanations

    code

    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
     yo
    -0.09
    ================
    -0.08
    ================================================================
    -0.08
    ================================
    -0.08
    ↵///
    -0.08
     посред
    -0.08
    <hr
    -0.08
     Colombo
    -0.08
     Hipp
    -0.08
    	end
    -0.08
    POSITIVE LOGITS
     apology
    0.08
    Pam
    0.08
    .Report
    0.08
    Aura
    0.08
     då
    0.07
    Fixed
    0.07
    rz
    0.07
    0.07
     Logistics
    0.07
    Markdown
    0.07
    Activations Density 0.001%

    No Known Activations