© 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. 68125
    Prev
    Next
    INDEX
    Explanations

    Odd, even numbers

    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
    	size
    -0.08
    ,size
    -0.08
    Iter
    -0.08
    мотрите
    -0.08
    матри
    -0.08
    _iteration
    -0.08
     gosto
    -0.08
     affid
    -0.08
     champs
    -0.08
    pring
    -0.08
    POSITIVE LOGITS
    normally
    0.08
     normally
    0.08
    atsis
    0.08
    (The
    0.07
    (In
    0.07
     sum
    0.07
     takeover
    0.07
    (By
    0.07
    essu
    0.07
    ess
    0.07
    Activations Density 0.014%

    No Known Activations