Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90065
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
    archical
    -0.08
    cade
    -0.07
    px
    -0.07
     공
    -0.07
    札
    -0.07
    'on
    -0.07
    oard
    -0.07
     Cala
    -0.07
    ૅ
    -0.07
     Merr
    -0.07
    POSITIVE LOGITS
    /dialog
    0.10
    Dialogue
    0.09
     sessions
    0.09
     dialogue
    0.09
     dialogues
    0.09
     ওঠ
    0.09
    Skype
    0.09
     Dialogue
    0.09
     Dialog
    0.08
     ಮಾತನಾಡ
    0.08
    Activations Density 0.008%

    No Known Activations