© 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. 5969
    Prev
    Next
    INDEX
    Explanations

    single letters

    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
     mehrere
    -0.08
     smokers
    -0.08
    alous
    -0.08
     trotzdem
    -0.08
    infeld
    -0.08
     imate
    -0.08
     dennoch
    -0.07
     hod
    -0.07
     imao
    -0.07
     prenez
    -0.07
    POSITIVE LOGITS
    ည
    0.08
     mall
    0.08
    Ark
    0.08
    _DECL
    0.08
    -bottom
    0.07
    trav
    0.07
    _BUSY
    0.07
    .mall
    0.07
    ்ந்து
    0.07
     vliegt
    0.07
    Activations Density 0.000%

    No Known Activations