© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64601
    Prev
    Next
    INDEX
    Explanations

    analysis

    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
     వచ్చింది
    -0.08
     వచ్చిన
    -0.08
    Setter
    -0.07
    として
    -0.07
    ann
    -0.07
    .response
    -0.07
    rotate
    -0.07
     receita
    -0.07
     duda
    -0.07
     wa
    -0.07
    POSITIVE LOGITS
    	Expect
    0.08
    걸
    0.08
     част
    0.08
     dreams
    0.07
     bisog
    0.07
     compuls
    0.07
     Expect
    0.07
     combatt
    0.07
     impedir
    0.07
     ಎಲ್ಲ
    0.07
    Activations Density 0.009%

    No Known Activations