© 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. 23-RESID-POST-AA
    11. 48161
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     বাদ
    -0.09
    adoo
    -0.08
    AGES
    -0.08
     Aguil
    -0.08
     ഒഴ
    -0.08
     പുറത്ത
    -0.07
     বার
    -0.07
     sudah
    -0.07
    оу
    -0.07
     എഴ
    -0.07
    POSITIVE LOGITS
    ürlüğ
    0.08
     circulated
    0.08
     teknik
    0.07
    atut
    0.07
     paranoid
    0.07
    hire
    0.07
     συν
    0.07
     Cina
    0.07
     equipped
    0.07
    	Null
    0.07
    Activations Density 0.000%

    No Known Activations