© 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. 48015
    Prev
    Next
    INDEX
    Explanations

    AP

    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
     его
    -0.09
    amation
    -0.08
    voet
    -0.08
     its
    -0.08
    orious
    -0.07
    ാദ
    -0.07
     તેના
    -0.07
    ensed
    -0.07
    -0.07
     considerando
    -0.07
    POSITIVE LOGITS
    PLIED
    0.15
    prentissage
    0.13
    prendre
    0.11
    PLIC
    0.11
    PLY
    0.11
    POINT
    0.11
    plied
    0.11
    plies
    0.10
    PRISE
    0.10
    EX
    0.10
    Activations Density 0.016%
    No Known Activations