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. 53260
    Prev
    Next
    INDEX
    Explanations

    Confirmations

    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
    871
    -0.08
     PRI
    -0.08
     wenig
    -0.08
     displacement
    -0.07
    Lim
    -0.07
     FIFO
    -0.07
    -0.07
     least
    -0.07
    Least
    -0.07
     harming
    -0.07
    POSITIVE LOGITS
     affirmative
    0.13
     Zustimmung
    0.12
    “Yes
    0.12
    _yes
    0.12
     bestät
    0.11
     afirm
    0.11
    认可
    0.10
    agree
    0.10
     соглас
    0.10
    回应
    0.10
    Activations Density 0.074%

    No Known Activations