© 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. 11-RESID-POST-AA
    11. 65040
    Prev
    Next
    INDEX
    Explanations

    AI image/content generation

    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
    dream
    -0.09
     Already
    -0.08
    equip
    -0.08
    steam
    -0.08
     Fert
    -0.08
     enable
    -0.08
     �
    -0.08
    ature
    -0.08
     നേത
    -0.08
    onten
    -0.07
    POSITIVE LOGITS
    出来
    0.09
     ממנו
    0.08
    .open
    0.08
     möglichst
    0.08
    .orig
    0.07
     according
    0.07
    ิต
    0.07
     מקור
    0.07
    יגן
    0.07
    ER
    0.07
    Activations Density 0.004%

    No Known Activations