© 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. 96744
    Prev
    Next
    INDEX
    Explanations

    T

    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
    EH
    -0.09
    AH
    -0.09
    OOD
    -0.08
    Agg
    -0.08
    AFF
    -0.08
    itulo
    -0.08
    CG
    -0.08
    OH
    -0.08
    ু
    -0.08
     maha
    -0.08
    POSITIVE LOGITS
    olkien
    0.19
    ennessee
    0.18
    rouvez
    0.18
    écn
    0.17
    entukan
    0.17
    amaño
    0.17
    EMPLATE
    0.17
    ässä
    0.16
    angent
    0.16
    inggi
    0.16
    Activations Density 0.035%

    No Known Activations