Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2371
    Prev
    Next
    INDEX
    Explanations

    here's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heavily
    -0.09
     प्रतिस
    -0.08
     použív
    -0.08
    sp
    -0.07
     implying
    -0.07
     benötigt
    -0.07
    िकी
    -0.07
     performed
    -0.07
     quar
    -0.07
     ades
    -0.07
    POSITIVE LOGITS
    Checklist
    0.09
    áng
    0.08
     Alleg
    0.08
     pró
    0.08
    Party
    0.08
     же
    0.08
    nonce
    0.08
     Marie
    0.07
    Mx
    0.07
     frit
    0.07
    Activations Density 0.015%

    No Known Activations