© 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. 95250
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
     parameter
    -0.09
     mach
    -0.08
    Parameter
    -0.08
     Eintritt
    -0.08
     cob
    -0.07
     STL
    -0.07
     ക്ര
    -0.07
    _View
    -0.07
    ADF
    -0.07
     SSL
    -0.07
    POSITIVE LOGITS
    回答
    0.09
    .responses
    0.08
     assisting
    0.08
     antwort
    0.08
     fent
    0.08
     replied
    0.08
     replying
    0.08
     hingegen
    0.08
     beantworten
    0.08
     sinister
    0.08
    Activations Density 0.114%

    No Known Activations