© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48691
    Prev
    Next
    INDEX
    Explanations

    ign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afft
    -0.08
    wärt
    -0.08
    hmen
    -0.07
    heus
    -0.07
    ers
    -0.07
    яд
    -0.07
    になります
    -0.07
     Ja
    -0.07
     jc
    -0.07
    jos
    -0.07
    POSITIVE LOGITS
    oring
    0.20
    ition
    0.19
    ored
    0.14
    ITION
    0.13
    orar
    0.11
    oration
    0.11
    orera
    0.10
    atius
    0.10
    orado
    0.10
    orning
    0.10
    Activations Density 0.001%

    No Known Activations