© 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. 47134
    Prev
    Next
    INDEX
    Explanations

    Contents

    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
     দুর
    -0.08
     நேர
    -0.08
     প্রশ
    -0.07
     Dix
    -0.07
     chickens
    -0.07
     predominant
    -0.07
     Mg
    -0.07
    န
    -0.07
    Constant
    -0.07
    Validity
    -0.07
    POSITIVE LOGITS
     Hastings
    0.08
    和值
    0.08
     �
    0.08
    strom
    0.08
    tryside
    0.08
    =*
    0.08
     पाने
    0.08
    jom
    0.08
     varten
    0.07
     visu
    0.07
    Activations Density 0.002%

    No Known Activations