© 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. 94799
    Prev
    Next
    INDEX
    Explanations

    counting

    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
     হয়ে
    -0.07
     sollic
    -0.07
     Abb
    -0.07
     foodie
    -0.07
     Gaz
    -0.07
    iframe
    -0.07
     Abr
    -0.07
    ADOR
    -0.07
     হও
    -0.07
     একটি
    -0.07
    POSITIVE LOGITS
     weighted
    0.09
     counting
    0.09
     cof
    0.08
    Multiplicity
    0.08
    Weighted
    0.08
     distinctions
    0.08
     multiplic
    0.08
     counted
    0.08
     учетом
    0.08
     alam
    0.08
    Activations Density 0.007%

    No Known Activations