© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45084
    Prev
    Next
    INDEX
    Explanations

    Playstation

    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
     routine
    -0.10
     routines
    -0.09
    Routine
    -0.08
     rutina
    -0.08
    -gl
    -0.08
     Routine
    -0.08
    shr
    -0.08
     페이지
    -0.07
     harmless
    -0.07
    Firm
    -0.07
    POSITIVE LOGITS
     Supports
    0.08
     aerospace
    0.08
     XF
    0.08
    овыми
    0.07
     Ogre
    0.07
    热
    0.07
     beliebtesten
    0.07
     قوات
    0.07
     headset
    0.07
    许可
    0.07
    Activations Density 0.003%

    No Known Activations