Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112346
    Prev
    Next
    INDEX
    Explanations

    Survey completion

    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
    оди
    -0.09
     আও
    -0.08
     agbara
    -0.08
     давление
    -0.08
     kira
    -0.08
    []={
    -0.08
     deuda
    -0.08
     VIH
    -0.08
     teme
    -0.08
     আয়োজন
    -0.08
    POSITIVE LOGITS
     respondent
    0.09
    answers
    0.09
     respondents
    0.09
    seq
    0.08
     답
    0.08
    回答
    0.08
     antwoorden
    0.08
     respostas
    0.08
     입력
    0.08
     answers
    0.08
    Activations Density 0.007%

    No Known Activations