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. 61075
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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
    _STANDARD
    -0.09
    medium
    -0.08
     будут
    -0.08
     medium
    -0.08
     Medium
    -0.07
    lant
    -0.07
    bah
    -0.07
    feer
    -0.07
     Dienste
    -0.07
     ಸೇರಿದಂತೆ
    -0.07
    POSITIVE LOGITS
     ટી
    0.07
     /↵
    0.07
     приема
    0.07
     soi
    0.07
     ovog
    0.07
    .idx
    0.07
     soja
    0.07
    ённых
    0.07
    .writer
    0.07
    }}>↵
    0.07
    Activations Density 0.893%

    No Known Activations