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. 42508
    Prev
    Next
    INDEX
    Explanations

    chemistry problems

    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
    णे
    -0.08
     timeless
    -0.08
     सत्य
    -0.08
    审
    -0.07
     disciplines
    -0.07
    ण्यासाठी
    -0.07
     framed
    -0.07
     уни
    -0.07
    Meet
    -0.07
     рам
    -0.07
    POSITIVE LOGITS
     iod
    0.12
     nitr
    0.11
     oxidation
    0.11
     bicarbon
    0.11
     impurities
    0.11
     peroxide
    0.10
     acidic
    0.10
     mixtures
    0.10
     alkoh
    0.10
     sediments
    0.10
    Activations Density 0.010%

    No Known Activations